VISTA-MED: Integrating AI-Based MRI Segmentation with Virtual Reality for Medical Education

Background Innovations in Artificial Intelligence (AI) and Virtual Reality (VR) are driving transformative changes in medical imaging and education by enabling automated segmentation and immersive visualization. Traditional anatomy and imaging instruction often lack spatial interactivity, limiting comprehension and diagnostic reasoning. This study introduces VISTA-MED, an integrated AI-VR platform designed to enhance medical imaging education through real-time MRI visualization and segmentation. Methods The system employs the nnU-Net architecture for automated segmentation of brain tumor regions using the BRATS2020 dataset. Preprocessing included bias field correction, image registration to the MNI152 template, and noise reduction. Segmentation outputs were converted into 3D-compatible formats and integrated into a Unity-based VR environment supporting interactive exploration of anatomical structures. Performance was evaluated using Dice coefficient, Intersection over Union (IoU), and precision-recall analysis. Results The segmentation model achieved a mean Dice score of 0.914, indicating high overlap between predicted masks and ground truth annotations. IoU values were consistent with Dice scores, confirming accurate delineation of tumor boundaries. Internal testing validated smooth rendering and stable frame rates in the VR environment, enabling real-time interaction without noticeable latency. Qualitative assessment confirmed anatomical fidelity of AI-generated masks. Conclusion VISTA-MED demonstrates the technical feasibility of combining AI-driven segmentation with immersive VR visualization for medical imaging education. This integration enhances spatial understanding and diagnostic reasoning, addressing limitations of traditional anatomy instruction. Future work will focus on usability studies, scalability, and educational impact assessment to support broader adoption in clinical and academic settings.